Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Prototypicality Bias Evaluation on ProtoBias Demography
Loading...
0.515
Correct Ranking Margin
GPT-4o
0.05116
0.17158
0.292
0.41242
Jan 8, 2026
Correct Ranking Margin
Incorrect Ranking Margin
Updated 4d ago
Evaluation Results
Method
Method
Links
Correct Ranking Margin
Incorrect Ranking Margin
GPT-4o
2026.01
0.515
0.272
GPT-5
2026.01
0.42
0.048
PROTOSCORE
2026.01
0.358
0.057
PickScore
2026.01
0.186
0.217
CLIPScore
2026.01
0.151
0.127
VQAScore
2026.01
0.069
0.124
Feedback
Search any
task
Search any
task